All‐Optical Autoencoder Machine Learning Framework Using Linear Diffractive Processors

Diffractive deep neural network (D2NN), known for its high speed and strong parallelism, is applied across various fields, including pattern recognition, image processing, and image transmission. However, existing network architectures primarily focus on data representation within the original domain, with limited exploration of the latent space, thereby restricting the information mining capabilities and multifunctional integration of D2NNs. Here, an all‐optical autoencoder (OAE) framework is proposed that linearly encodes the input wavefield into a prior shape distribution in the diffractive latent space (DLS) and decodes the encoded pattern back to the original wavefield. By leveraging the bidirectional multiplexing property of D2NN, the OAE modelsfunction as encoders in one direction and as decoders in the opposite direction. The models are applied to three areas: image denoising, noise‐resistant reconfigurable image classification, and image generation. Proof‐of‐concept experiments are conducted to validate numerical simulations. The OAE framework exploits the potential of latent representations, enabling single set of diffractive processors to simultaneously achieve image reconstruction, representation, and generation. This work not only offers fresh insights into the design of optical generative models but also paves the way for developing multifunctional, highly integrated, and general optical intelligent systems.